RehmanKhalid/Qwen3.5-0.8B-CommonsenseQA-LoRA

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base_id = "Qwen/Qwen3.5-0.8B"
adapter_id = "RehmanKhalid/Qwen3.5-0.8B-CommonsenseQA-LoRA"

tokenizer = AutoTokenizer.from_pretrained(base_id)
model = AutoModelForCausalLM.from_pretrained(
    base_id,
    torch_dtype="auto",
    device_map="auto",
)
model = PeftModel.from_pretrained(model, adapter_id)
model.eval()

messages = [
    {
        "role": "system",
        "content": "You are a helpful assistant. Answer with only the letter (A, B, C, D, or E).",
    },
    {
        "role": "user",
        "content": (
            "Question: A revolving door is convenient for two direction travel, "
            "but it also serves as a security measure at a what?\n"
            "A) bank\n"
            "B) library\n"
            "C) department store\n"
            "D) mall\n"
            "E) new york\n"
            "Answer:"
        ),
    },
]

prompt = tokenizer.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)

with torch.no_grad():
    outputs = model.generate(**inputs, max_new_tokens=4, do_sample=False)

print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))